Pregled bibliografske jedinice broj: 697272
Adaptive Bidding for Electricity Wholesale Markets in a Smart Grid
Adaptive Bidding for Electricity Wholesale Markets in a Smart Grid // Proceedings of the Workshop on Agent-Mediated Electronic Commerce and Trading Agent Design and Analysis (AMEC/TADA 2014) @ AAMAS 2014 / Ceppi, S. ; David, E. ; Robu, V., Shehory O. ; Vetsikas, I.A. (ur.).
Pariz: International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2014. str. 1-14 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 697272 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Adaptive Bidding for Electricity Wholesale Markets in a Smart Grid
Autori
Babić, Jurica ; Podobnik, Vedran
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the Workshop on Agent-Mediated Electronic Commerce and Trading Agent Design and Analysis (AMEC/TADA 2014) @ AAMAS 2014
/ Ceppi, S. ; David, E. ; Robu, V., Shehory O. ; Vetsikas, I.A. - Pariz : International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2014, 1-14
ISBN
978-1-4503-2738-1
Skup
Workshop on Agent-Mediated Electronic Commerce and Trading Agent Design and Analysis (AMEC/TADA 2014) @ AAMAS 2014
Mjesto i datum
Pariz, Francuska, 05.05.2014
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
smart grids ; software agents ; electricity wholesale market ; reinforcement learning ; Power Trading Agent Competition
Sažetak
One of challenges for researchers in smart grids is to find mechanisms for putting orders on the electricity wholesale market. This paper tackles this problem by proposing adaptive bidding mechanism for trading in the wholesale market. The research challenge lies in the fact that wholesale players simultaneously trade on 24 different wholesale markets determined by the moment of electricity delivery which ranges from 1 to 24 hours ahead. Namely, the variant Roth-Erev reinforcement learning algorithm is used to coordinate wholesale bidding across different markets by choosing among four implemented wholesale strategies. The Power Trading Agent Competition is used to evaluate the performance of different implementations of the adaptive bidding mechanism as well as to benchmark adaptive bidding approach against single strategy approach.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo, Ekonomija
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb